Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.

Deep Learning for Vision Systems

  • Course Code: Artificial Intelligence - Deep Learning for Vision Systems
  • Course Dates: Contact us to schedule.
  • Course Category: AI / Machine Learning Duration: 2 Days Audience: This course is geared for Python developers, analysts or others who wants to get concepts and tools for building intelligent, scalable computer vision systems that can identify and react to objects in images, videos, and real life

Course Snapshot 

  • Duration: 2 days 
  • Skill-level: Foundation-level Deep Learning for Vision Systems skills for Intermediate skilled team members. This is not a basic class. 
  • Targeted Audience: This course is geared for Python developers, analysts or others who wants to get concepts and tools for building intelligent, scalable computer vision systems that can identify and react to objects in images, videos, and real life 
  • Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required. 
  • Delivery Format: This course is available for onsite private classroom presentation, or remote instructor led delivery, or CBT/WBT (by request). 
  • Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals. 

Deep Learning for Vision Systems teaches you to apply deep learning techniques to solve real-world computer vision problems. In his straightforward and accessible style, DL and CV expert Mohamed Elgendy introduces you to the concept of visual intuition—how a machine learns to understand what it sees. Then you’ll explore the DL algorithms used in different CV applications. You’ll drill down into the different parts of the CV interpreting system, or pipeline. Using Python, OpenCV, Keras, TensorFlow, and Amazon’s Mx Net, you’ll discover advanced DL techniques for solving CV problems. Applications of focus include image classification, segmentation, captioning, and generation as well as face recognition and analysis. You’ll also cover the most important deep learning architectures including artificial neural networks (ANNs), convolutional networks (CNNs), and recurrent networks (RNNs), knowledge that you can apply to related deep learning disciplines like natural language processing and voice user interface. Real-life, scalable projects from Amazon, Google, and Facebook drive it all home. With this invaluable course, you’ll gain the essential skills for building amazing end-to-end CV projects that solve real-world problems. 

Working in a hands-on learning environment, led by our Deep Learning expert instructor, students will learn about and explore: 

  • explore the DL algorithms used in different CV applications.  
  • You’ll drill down into the different parts of the CV interpreting system, or pipeline. Using Python, OpenCV, Keras, TensorFlow, and Amazon’s Mx Net,  
  • you’ll discover advanced DL techniques for solving CV problems. 

Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below 

  • Introduction to computer vision 
  • Deep learning and neural networks 
  • Transfer learning and advanced CNN architectures 
  • Image classification and captioning 
  • Object detection with YOLO, SSD and R-CNN 
  • Style transfer 
  • AI ethics 
  • Real-world projects 

Audience & Pre-Requisites 

This course is geared for attendees with Python skills who wish to get concepts and tools for building intelligent, scalable computer vision systems that can identify and react to objects in images, videos, and real life 

Pre-Requisites:  Students should have  

  • with intermediate Python, math and machine learning skills.  
  • Experience with the Matplotlib and Pandas machine learning libraries is helpful 
  • Good foundational mathematics or logic skills 
  • Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su 

Course Agenda / Topics 

  1. Welcome to Computer Vision 
  • Computer vision intuition 
  • Applications of computer vision 
  • Computer Vision Pipeline – The big picture 
  • Input image 
  • Image preprocessing 
  • Feature extraction 
  • Classifier learning algorithm 
  • Ch summary and takeaways 
  1. Deep learning and neural networks 
  • The Perceptron intuition 
  • Multi-Layer Perceptron (MLP) 
  • Activation functions 
  • Feedforward 
  • Error functions 
  • Optimization algorithms 
  • Backpropagation 
  • Ch summary and takeaways 
  • Project: Build Your first Neural Network 
  1. Convolutional Neural Networks (CNNs) 
  • Image classification using MLP 
  • CNNs Architecture 
  • Basic components of the CNN 
  • Image classification using CNNs 
  • Add Dropout layers to avoid overfitting 
  • Convolution over colored images (3D images) 
  • Ch summary and takeaways 
  • Project: Image classification for colored images (CIFAR-10 dataset) 
  1. Structuring Deep Learning Projects and Hyperparameters tuning 
  • Define the performance metrics 
  • Design a baseline model 
  • Get your data ready for training 
  • Evaluate the model and interpret its performance (error analysis) 
  • Improve the network and tune hyperparameters 
  • Batch normalization (BN) 
  • Ch summary and takeaways 
  • Project: Achieve >90% accuracy on the CIFAR-10 image classification project 
  1. Advanced CNN Architectures 
  • CNN design patterns 
  • LeNet-5 
  • VGGNet 
  • Inception and Google Net 
  • Res Net 
  1. Transfer Learning 
  • What are the problems that transfer learning is solving? 
  • What is transfer learning? 
  • How transfer learning works 
  • Transfer learning approaches 
  • Choose the appropriate level of transfer learning 
  • Open-source datasets 
  • Ch summary and takeaways 
  • Project 1: A pretrained network as a feature extractor 
  • Project 2: Fine tuning 
  1. Object Detection with R-CNN, SSD, and YOLO 
  • General object detection framework 
  • Region-Based Convolutional Neural Networks (R-CNNs) 
  • Single Shot Detection (SSD) 
  • Ch summary and takeaways 
  1. Generative Adversarial Networks (GANs) 
  • GANs Architecture 
  • Evaluate GAN models 
  • Popular GANs Applications 
  • Building your own GAN project 
  1. Deep Dream and Neural Style Transfer 
  • How convolutional neural networks see the world 
  • Deep Dream 
  • Neural Style Transfer 
View All Courses

    Course Inquiry

    Fill in the details below and we will get back to you as quickly as we can.

    Interested in any of these related courses?